build-dashboard

Build an interactive HTML dashboard with charts, filters, and tables. Use when creating an executive overview with KPI cards, turning query results into a shareable self-contained report, building a team monitoring snapshot, or needing multiple charts with filters in one browser-openable file.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable with complete, executable templates and clear sequencing, but the skill is a monolithic ~950-line document with weak validation checkpoints and no progressive disclosure into reference files. It earns its actionability but pays for verbosity and lack of file-splitting.

Suggestions

Move the full CSS styling block and complete Chart.js chart implementations into reference files (e.g., references/template.html, references/charts.js) and link to them from the body to cut inline bulk and improve progressive disclosure.

Add an explicit validation/checkpoint step to the workflow — e.g., 'Open the file and check the browser console for JS errors; fix and re-open before delivering' — with a validate→fix→retry loop rather than the single vague 'Confirm it renders correctly'.

Consolidate the chart-type list (step 5) with the matching Chart.js implementation patterns so each type is documented once, trimming redundant tokens.

Dimension	Reasoning	Score
Conciseness	The ~950-line body is mostly efficient, executable code, but large inline blocks (the full CSS color/layout system, multiple complete Chart.js implementations, performance tables) inflate the token budget and could be tightened or offloaded.	2 / 3
Actionability	Provides fully executable, copy-paste-ready guidance throughout — concrete qsv commands, a complete HTML base template, working Chart.js functions, and ready-to-use CSS. Nothing is pseudocode or hand-waved.	3 / 3
Workflow Clarity	The 7-step workflow is clearly sequenced, but the only checkpoint is the vague 'Confirm it renders correctly' (step 7); there is no explicit validate→fix→retry loop (e.g., checking the browser console for JS errors before delivering).	2 / 3
Progressive Disclosure	Sections are well-organized, but everything lives inline in one monolithic SKILL.md with no bundle files; content that should be separate (full CSS, chart implementations, performance reference) is not split out into referenced files.	2 / 3
	Total	9 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: it states concrete capabilities in third-person/imperative voice and provides an explicit 'Use when' clause with several natural trigger scenarios. No vagueness, over-claims, or first/second-person voice to penalize.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Build an interactive HTML dashboard with charts, filters, and tables' — naming specific output components rather than abstract capabilities.	3 / 3
Completeness	Explicitly answers both what ('Build an interactive HTML dashboard with charts, filters, and tables') and when ('Use when creating an executive overview...').	3 / 3
Trigger Term Quality	Covers natural terms users would say — 'executive overview with KPI cards', 'query results', 'shareable self-contained report', 'team monitoring snapshot', 'multiple charts with filters in one browser-openable file'.	3 / 3
Distinctiveness Conflict Risk	Has a clear niche — self-contained browser-openable HTML dashboards — with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (951 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: dathere/qsv
Path: .claude/skills/build-dashboard/SKILL.md
Commit: 17c10db

Reviewed: about 5 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.